s10_run_xgboost.py 文件源码

def run_test_with_model(train, test, features, target, random_state=0):
    start_time = time.time()
    test_size = 0.02

    # X_train, X_valid = train_test_split(train, test_size=test_size, random_state=random_state)
    split = round((1-test_size)*len(train.index))
    X_train = train[0:split]
    X_valid = train[split:]
    print('Length train:', len(X_train.index))
    print('Length valid:', len(X_valid.index))

    # watchlist = [(dtrain, 'train'), (dvalid, 'eval')]
    # gbm = xgb.train(params, dtrain, num_boost_round, evals=watchlist, early_stopping_rounds=early_stopping_rounds, feval=auc_xgboost, verbose_eval=True)
    # gbm = xgb.train(params, dtrain, num_boost_round, evals=watchlist, early_stopping_rounds=early_stopping_rounds, verbose_eval=True)
    gbm = xgb.Booster()
    gbm.load_model("models/model_0.968276662916_eta_0.2_md_5_test_size_0.02.bin")

    print("Validating...")
    check = gbm.predict(xgb.DMatrix(X_valid[features]))
    score = roc_auc_score(X_valid[target].values, check)
    score_kaggle = auc(X_valid[target].values, check)
    print('Check error value: {:.6f} (Kaggle: {:.6f})'.format(score, score_kaggle))

    imp = get_importance(gbm, features)
    print('Importance array: ', imp)

    print("Predict test set...")
    test_prediction = gbm.predict(xgb.DMatrix(test[features]))

    print('Training time: {} minutes'.format(round((time.time() - start_time)/60, 2)))
    return test_prediction.tolist(), score